asknicely

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly shows fetching user-generated survey responses and other AskNicely data via Membrane actions (e.g., "Get Survey Responses") and direct proxy requests ("membrane request CONNECTION_ID /path/to/endpoint"), meaning the agent will ingest third-party user content from AskNicely APIs that could influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:59 AM